Python 网络爬虫(二) 拉勾网

本案例仅用于学术交流!

原文地址 https://github.com/fuyunzhishang/python-spider
效果图
爬取第二页的时候会提示操作太频繁,后期会考虑优化方案
import  re
import  time
import  requests
import  xlsxwriter

from  bs4 import BeautifulSoup
from  collections import  Counter

BASE_URL = "https://www.lagou.com/jobs/positionAjax.json?city=%E5%8C%97%E4%BA%AC&needAddtionalResult=false"
def get_page(base_url,pn,keyword):

    if pn == 1:
        boo = True
    else:
        boo = False
    # proxies = {
    #     "http":"http://61.135.217.7:80",
    # }
    formdata = {
        "first":boo,
        "pn": pn,
        "kd": keyword,
    }

    headers = {
        "Content-Length": str(len(formdata)),
        "Host": "www.lagou.com",
        "Origin": "https://www.lagou.com",
        "Referer": "https://www.lagou.com/jobs/list_Python?city=%E5%8C%97%E4%BA%AC&cl=false&fromSearch=true&labelWords=&suginput=",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 Safari/537.36",
        "X - Anit - Forge - Code": "0",
        "X - Anit - Forge - Token": None,
        "X - Requested - With": "XMLHttpRequest",

    }

    req = requests.post(url=BASE_URL,headers=headers,data=formdata)#proxies=proxies

    json_req = req.json()
    print("----------------------------{}".format(json_req))

    # soup = BeautifulSoup(req.content,'lxml')
    # content = soup.select("p")
    # print(type(json_req)) #<class 'dict'>
    return  json_req

# 获取 PositionId
def read_positionId(json_req):

    tag = "positionId"
    # page_json = json.loads(soup)
    page_json = json_req['content']['positionResult']['result']
    company_list  = []
    for i in range(0,15): #查询列表每页展示15条
        # print("company_list_positionId = {}".format(page_json[i].get(tag)))
        company_list.append(page_json[i].get(tag))

    return  company_list


# 合成目标url
# 获取职位详情 由positionId 和 BaseUrl 组成
def get_content(positionId):
    detail_page_url =r"https://www.lagou.com/jobs/{}.html".format(positionId)
    print("detail_page_url....{}".format(detail_page_url))
    headers = {
        "Host": "www.lagou.com",
        "Referer":detail_page_url,
        "Upgrade-Insecure-Requests": "1",
        "User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 Safari/537.36"

    }

    req = requests.get(detail_page_url,headers=headers)
    return  req

# 对数据进行清洗,获取职位描述信息
def get_result(content):
    soup = BeautifulSoup(content.content, 'lxml')
    # print("soup...{}".format(soup))
    job_description = soup.find("dd", attrs={"class": "job_bt"})
    # job_description = soup.select("dd[class='job_bt']")  #list
    # print("job_description...{}".format(job_description))
    job_description = str(job_description)
    rule = re.compile(r'<[^>]+>')
    result = rule.sub(' ', job_description)
    # print("job_description...result:{}".format(result))
    return result


# 筛选关键词,得到技能关键词

def get_search_skill(result):
    rule = re.compile(r'[a-zA-Z]+')
    skill_list = rule.findall(result)

    # print("get_search_skill...{}".format(skill_list))
    return  skill_list


# 对关键词计数,并排序,选取频次排序Top80 的关键词作为样本

def count_skill_list(skill_list):
    skill_lower = [i.lower() for i in skill_list] #list 元素转换小写
    count_dict = Counter(skill_lower).most_common(80)
    # print("count_skill_list...",count_dict)  #[('waf', 2), ('php', 1), ('python', 1), ('go', 1), ('java', 1), ('nginx', 1), ('lua', 1)]

    return  count_dict

# 对结果进行存储并可视化处理 生成area 图
def save_excel(count_dict,file_name):
    book = xlsxwriter.Workbook(r'F:\lagou_project\com\lagou\spider\{}.xls'.format(file_name))  #创建你的.xlsx文件
    tmp = book.add_worksheet() #增加sheet
    row_num = len(count_dict)
    for i in range(1,row_num):
        if i == 1:
            tag_pos = 'A%s' % i
            tmp.write_row(tag_pos,['关键词','频次'])
        else:
            con_pos = 'A%s' % i
            k_v = list(count_dict[i-2])
            tmp.write_row(con_pos,k_v)

    chart1 = book.add_chart({'type':'area'}) #在工作表中创建一个图表对象
    chart1.add_series({
        'name':'=Sheet1!$B$1',
        'categories':'=Sheet1!$A$2:$A$80',
        'values':'=Sheet1!$B$2:$B$80'
    })

    chart1.set_title({'name':'关键词排名'})
    chart1.set_x_axis({'name':'关键词'})
    chart1.set_y_axis({'name':'频次(/次)'})

    tmp.insert_chart('C2',chart1,{'x_offset':15,'y_offset':10})

    book.close()


if __name__ == '__main__':
    keyword = input("请输入你想查询的关键字:")
    all_skill_list = [] #关键词总表
    for i in range(1,30):
        time.sleep(3)
        print("************************正在抓取第 {} 页{} *************************".format(i,keyword))
        soup = get_page(BASE_URL,pn=i,keyword=keyword)
        company_list = read_positionId(soup)
        for id in company_list:
            req = get_content(id)
        #     print(content)
        #     req = get_content("4904310")
            result = get_result(req)
            skill_list = get_search_skill(result)
            all_skill_list.extend(skill_list)
        # print(skill_list)
    count_dict = count_skill_list(all_skill_list)
            # print("===={}".format(count_dict))
    save_excel(count_dict,'0917')
Python 网络爬虫(二) 拉勾网

本案例仅用于学术交流!

猜你喜欢
